[PATCH] D17943: [Aarch64] Add pass LoopDataPrefetch for Cyclone

[Adam Nemet via llvm-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rL263770: [Aarch64] Add pass LoopDataPrefetch for Cyclone (authored by anemet).

Changed prior to commit:
  http://reviews.llvm.org/D17943?vs=50002&id=51001#toc

Repository:
  rL LLVM

http://reviews.llvm.org/D17943

Files:
  llvm/trunk/lib/Target/AArch64/AArch64TargetMachine.cpp
  llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
  llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.h

Index: llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.h
===================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.h
+++ llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.h
@@ -127,6 +127,10 @@
   int getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy, unsigned Factor,
                                  ArrayRef<unsigned> Indices, unsigned Alignment,
                                  unsigned AddressSpace);
+
+  unsigned getCacheLineSize();
+
+  unsigned getPrefetchDistance();
   /// @}
 };
 
Index: llvm/trunk/lib/Target/AArch64/AArch64TargetMachine.cpp
===================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64TargetMachine.cpp
+++ llvm/trunk/lib/Target/AArch64/AArch64TargetMachine.cpp
@@ -101,6 +101,11 @@
 EnableGlobalMerge("aarch64-global-merge", cl::Hidden,
                   cl::desc("Enable the global merge pass"));
 
+static cl::opt<bool>
+    EnableLoopDataPrefetch("aarch64-loop-data-prefetch", cl::Hidden,
+                           cl::desc("Enable the loop data prefetch pass"),
+                           cl::init(false));
+
 extern "C" void LLVMInitializeAArch64Target() {
   // Register the target.
   RegisterTargetMachine<AArch64leTargetMachine> X(TheAArch64leTarget);
@@ -236,6 +241,14 @@
   if (TM->getOptLevel() != CodeGenOpt::None && EnableAtomicTidy)
     addPass(createCFGSimplificationPass());
 
+  // Run LoopDataPrefetch for Cyclone (the only subtarget that defines a
+  // non-zero getPrefetchDistance).
+  //
+  // Run this before LSR to remove the multiplies involved in computing the
+  // pointer values N iterations ahead.
+  if (TM->getOptLevel() != CodeGenOpt::None && EnableLoopDataPrefetch)
+    addPass(createLoopDataPrefetchPass());
+
   TargetPassConfig::addIRPasses();
 
   // Match interleaved memory accesses to ldN/stN intrinsics.
Index: llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -20,6 +20,11 @@
 
 #define DEBUG_TYPE "aarch64tti"
 
+static cl::opt<unsigned> CyclonePrefetchDistance(
+    "cyclone-prefetch-distance",
+    cl::desc("Number of instructions to prefetch ahead for Cyclone"),
+    cl::init(280), cl::Hidden);
+
 /// \brief Calculate the cost of materializing a 64-bit value. This helper
 /// method might only calculate a fraction of a larger immediate. Therefore it
 /// is valid to return a cost of ZERO.
@@ -573,3 +578,15 @@
   }
   return true;
 }
+
+unsigned AArch64TTIImpl::getCacheLineSize() {
+  if (ST->isCyclone())
+    return 64;
+  return BaseT::getCacheLineSize();
+}
+
+unsigned AArch64TTIImpl::getPrefetchDistance() {
+  if (ST->isCyclone())
+    return CyclonePrefetchDistance;
+  return BaseT::getPrefetchDistance();
+}


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D17943.51001.patch
Type: text/x-patch
Size: 2968 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160318/7714eb1b/attachment.bin>